Machine Learning Engineer

At Levi Strauss & Co, we are revolutionising the apparel business and redefining the way denim is made. We are taking one of the world’s most iconic brands into the next century: from creating machine learning-powered denim finishes to using block-chain for our factory workers’ wellbeing, to building algorithms to better meet the needs of our consumers and optimize our supply chain. 

Be a pioneer in the fashion industry by joining our Digital and Technology organization where you will have the chance to build exciting solutions that will impact our global business and at the be part of large and diverse data community. 

The Data Science, analytics and AI team at Levi’s is responsible of building data-driven solutions that improve our existing business processes in multiple areas across supply chain, retail, revenue management and ecommerce, among others. The team is responsible for the end-to-end solution development from data ingestion until operationalisation of models in production.  As a Machine Learning Engineer within this org, you will work alongside Data Scientists, Analysts, ML engineers and product management to operationalise our ML models in production on a broad set of domains, powering a data-driven transformation of our standard business procedures across channels and organizations. You will develop and deploy novel approaches to optimize existing machine learning systems to maximise their value and increase consumer satisfaction at every brand touchpoint. We need someone who will bring thoughtful solutions, perspective, empathy, creativity, and a positive attitude to solve the different challenges in our business.  

You are a team player, always willing to work alongside and support your colleagues, you have a proactive and self-driven mindset towards problem-solving, looking to take on challenges and the opportunity to grow, and you are able to effectively balance solution vs risk taking. 

Key responsibilities:

• Work with data scientists , analysts, ML engineers and product management to create and deploy new models and ML systems. 

• Implement end-to-end solutions across the full breadth of ML model development lifecycle. The specific role includes working hand in hand with the scientists from the point of data exploration for model development to the point of building features, ML pipelines and deploying them in production. You will have an opportunity to work on both batch and real time models. The role also involves operational support. 

• Identify new opportunities to improve existing solutions towards greater accuracy and/or efficiency 

• Establish scalable, efficient, automated processes for data analyses, model development, validation and implementation 

• Write efficient and scalable software to ship products in an iterative, continual-release environment 

• Write optimized data pipelines to support machine learning models 

• Contribute to and promote good software engineering practices across the team and build cloud native software for ML pipelines 

• Contribute to and re-use community best practices 

Example Projects 

• Besides driving the transformation of Levi's into a data-driven enterprise in general, here are some specific projects you will work on and contribute to: 

• Pricing elasticity modelling and pricing recommendations 

• Promotional campaigns optimization and discounts recommendations 

• Analytics solutions to support revenue management activities  

About You 

• University or advanced degree in engineering, computer science, mathematics, or a related field 

• 3+ years' experience developing and deploying machine learning systems into production 

• Expertise in data engineering, analysis and processing (e.g. designing and maintaining ETLs, validating data and detecting quality issues)  

• Previous experience developing predictive models in a production environment, MLOps and model integration into larger scale applications.  

• Experience working with big data tools: Spark, Hadoop, Kafka, etc. 

• Experience with at least one cloud provider solution (AWS, GCP, Azure) and understanding of serverless code development. GCP experience preferred. 

• Efficiency with object-oriented/object function scripting languages, Python required. 

• Efficiency with Python data-handling libraries like Pandas or Pyspark. 

• Efficiency in SQL for data consumption and transformation. Nice to have: SparkSQL, BigQuery SQL dialects. 

• Expertise in standard software engineering methodology, e.g. unit testing, test automation, continuous integration, continuous deployment, code reviews, design documentation 

• Working experience with native ML orchestration systems such as Kubeflow, Vertex AI Pipelines, Airflow, TFX... 

• Relevant working experience with Docker and Kubernetes is a big plus.